Research map / Federated learning and privacy / Differential privacy
Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs
Zhongjie Shi, Puyu Wang, Chenyang Zhang, Yuan Cao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Gaussian gradient noise (DP-GD instead of GD) | two-layer CNN · synthetic task, sigma_p=0.5 (low SNR) | test accuracy (%): 75 -> 95 | Improved |
| add Gaussian gradient noise (DP-GD instead of GD) | two-layer CNN · synthetic task, sigma_p=0.3 | test accuracy (%): 95 -> 100 | Improved |
| add Gaussian gradient noise (DP-GD instead of GD) | two-layer CNN · synthetic task, sigma_p=0.1 (high SNR) | test accuracy | No clear effect |
| add Gaussian gradient noise (DP-GD instead of GD) | two-layer CNN · synthetic task, all noise levels | training loss | No clear effect |
Closest papers by meaning
- Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach (ICLR 2024 · similarity 0.88)
- Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy (NeurIPS 2025 · similarity 0.88)
- Rethinking DP-SGD in Discrete Domain: Exploring Logistic Distribution in the Realm of signSGD (ICML 2024 · similarity 0.88)
- DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction (NeurIPS 2024 · similarity 0.87)
- The importance of feature preprocessing for differentially private linear optimization (ICLR 2024 · similarity 0.87)
- Nearly Tight Black-Box Auditing of Differentially Private Machine Learning (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
